| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 9.606612205505371, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 3.9112, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 10.46530532836914, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 3.3471, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 10.344703674316406, | |
| "learning_rate": 0.0, | |
| "loss": 3.0781, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 15, | |
| "total_flos": 814916097146880.0, | |
| "train_loss": 3.4454755783081055, | |
| "train_runtime": 76.9751, | |
| "train_samples_per_second": 3.118, | |
| "train_steps_per_second": 0.195 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 814916097146880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |